Deep Learning Approaches for MR Image Reconstruction MS65

We propose and compare two different machine learning approaches for cardiac MR image reconstruction. The first class of approaches uses dictionary learning techniques for compressed sensing MR image reconstruction. The second class of approaches uses convolutional neural networks for MR image reconstruction. We evaluate both approaches in terms of reconstruction quality and computational speed.

This presentation is part of Minisymposium “MS65 - Machine learning techniques for image reconstruction (2 parts)
organized by: Markus Haltmeier (University Innsbruck) , Linh Nguyen (University of Idaho) .

Daniel Rueckert (Imperial College London)
deep learning, image reconstruction, machine learning